QE-BEV: Query Evolution for Bird's Eye View Object Detection in Varied Contexts
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929436011528192 |
|---|---|
| author | Yao, Jiawei Lai, Yingxin Kou, Hongrui Wu, Tong Liu, Ruixi |
| author_facet | Yao, Jiawei Lai, Yingxin Kou, Hongrui Wu, Tong Liu, Ruixi |
| contents | 3D object detection plays a pivotal role in autonomous driving and robotics, demanding precise interpretation of Bird's Eye View (BEV) images. The dynamic nature of real-world environments necessitates the use of dynamic query mechanisms in 3D object detection to adaptively capture and process the complex spatio-temporal relationships present in these scenes. However, prior implementations of dynamic queries have often faced difficulties in effectively leveraging these relationships, particularly when it comes to integrating temporal information in a computationally efficient manner. Addressing this limitation, we introduce a framework utilizing dynamic query evolution strategy, harnesses K-means clustering and Top-K attention mechanisms for refined spatio-temporal data processing. By dynamically segmenting the BEV space and prioritizing key features through Top-K attention, our model achieves a real-time, focused analysis of pertinent scene elements. Our extensive evaluation on the nuScenes and Waymo dataset showcases a marked improvement in detection accuracy, setting a new benchmark in the domain of query-based BEV object detection. Our dynamic query evolution strategy has the potential to push the boundaries of current BEV methods with enhanced adaptability and computational efficiency. Project page: https://github.com/Jiawei-Yao0812/QE-BEV |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_05989 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | QE-BEV: Query Evolution for Bird's Eye View Object Detection in Varied Contexts Yao, Jiawei Lai, Yingxin Kou, Hongrui Wu, Tong Liu, Ruixi Computer Vision and Pattern Recognition 3D object detection plays a pivotal role in autonomous driving and robotics, demanding precise interpretation of Bird's Eye View (BEV) images. The dynamic nature of real-world environments necessitates the use of dynamic query mechanisms in 3D object detection to adaptively capture and process the complex spatio-temporal relationships present in these scenes. However, prior implementations of dynamic queries have often faced difficulties in effectively leveraging these relationships, particularly when it comes to integrating temporal information in a computationally efficient manner. Addressing this limitation, we introduce a framework utilizing dynamic query evolution strategy, harnesses K-means clustering and Top-K attention mechanisms for refined spatio-temporal data processing. By dynamically segmenting the BEV space and prioritizing key features through Top-K attention, our model achieves a real-time, focused analysis of pertinent scene elements. Our extensive evaluation on the nuScenes and Waymo dataset showcases a marked improvement in detection accuracy, setting a new benchmark in the domain of query-based BEV object detection. Our dynamic query evolution strategy has the potential to push the boundaries of current BEV methods with enhanced adaptability and computational efficiency. Project page: https://github.com/Jiawei-Yao0812/QE-BEV |
| title | QE-BEV: Query Evolution for Bird's Eye View Object Detection in Varied Contexts |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2310.05989 |